We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251 percent, surpassing the winning entry of 2016 by a relative improvement of ${\sim }$ ∼ 25 percent. Models and code are available at https://github.com/hujie-frank/SENet .

/pdf/squeeze-and-excitation-networks-50icgwqgeu.pdf

Squeeze-and-Excitation Networks

While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort1–4, the structures of around 100,000 unique proteins have been determined5, but this represents a small fraction of the billions of known protein sequences6,7. Structural coverage is bottlenecked by the months to years of painstaking effort required to determine a single protein structure. Accurate computational approaches are needed to address this gap and to enable large-scale structural bioinformatics. Predicting the three-dimensional structure that a protein will adopt based solely on its amino acid sequence—the structure prediction component of the ‘protein folding problem’8—has been an important open research problem for more than 50 years9. Despite recent progress10–14, existing methods fall far short of atomic accuracy, especially when no homologous structure is available. Here we provide the first computational method that can regularly predict protein structures with atomic accuracy even in cases in which no similar structure is known. We validated an entirely redesigned version of our neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experimental structures in a majority of cases and greatly outperforming other methods. Underpinning the latest version of AlphaFold is a novel machine learning approach that incorporates physical and biological knowledge about protein structure, leveraging multi-sequence alignments, into the design of the deep learning algorithm. AlphaFold predicts protein structures with an accuracy competitive with experimental structures in the majority of cases using a novel deep learning architecture.

/pdf/highly-accurate-protein-structure-prediction-with-alphafold-2xjbzfwu3n.pdf

Highly accurate protein structure prediction with AlphaFold

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

An image input is obtained from a computing device when an image sensor of the computing device is directed to a scene. At least an object of interest in the scene is determined, and a label is determined for the object of interest. A search input is received from the computing device, where the search input is obtained from a mechanism other than the image sensor. An ambiguity is determined from the search input. A search query is determined that augments or replaces the ambiguity based at least in part on the label. A search result is based on the search query.

Using sensor inputs from a computing device to determine search query

Training image sampling

In apparel recognition, deep neural network models are often trained separately for different verticals (e.g. [7]). However, using specialized models for different verticals is not scalable and expensive to deploy. This paper addresses the problem of learning one unified embedding model for multiple object verticals (e.g. all apparel classes) without sacrificing accuracy. The problem is tackled from two aspects: training data and training difficulty. On the training data aspect, we figure out that for a single model trained with triplet loss, there is an accuracy sweet spot in terms of how many verticals are trained together. To ease the training difficulty, a novel learning scheme is proposed by using the output from specialized models as learning targets so that L2 loss can be used instead of triplet loss. This new loss makes the training easier and make it possible for more efficient use of the feature space. The end result is a unified model which can achieve the same retrieval accuracy as a number of separate specialized models, while having the model complexity as one.

/pdf/learning-unified-embedding-for-apparel-recognition-25j5v2oae8.pdf

Learning Unified Embedding for Apparel Recognition

We present TubeFormer-DeepLab, the first attempt to tackle multiple core video segmentation tasks in a unified manner. Different video segmentation tasks (e.g., video semantic/instance/panoptic segmentation) are usually considered as distinct problems. State-of-the-art models adopted in the separate communities have diverged, and radically different approaches dominate in each task. By contrast, we make a crucial observation that video segmentation tasks could be generally formulated as the problem of assigning different predicted labels to video tubes (where a tube is obtained by linking segmentation masks along the time axis) and the labels may encode different values depending on the target task. The observation motivates us to develop TubeFormer-DeepLab, a simple and effective video mask transformer model that is widely applicable to multiple video segmentation tasks. TubeFormer-DeepLab directly predicts video tubes with task-specific labels (either pure semantic categories, or both semantic categories and instance identities), which not only significantly simplifies video segmentation models, but also advances state-of-the-art results on multiple video segmentation benchmarks.

TubeFormer-DeepLab: Video Mask Transformer

A system and computer-implemented method for associating images with semantic entities and providing search results using the semantic entities. An image database contains one or more source images associated with one or more images labels. A computer may generate one or more documents containing the labels associated with each image. Analysis may be performed on the one or more documents to associate the source images with semantic entities. The semantic entities may be used to provide search results. In response to receiving a target image as a search query, the target image may be compared with the source images to identify similar images. The semantic entities associated with the similar images may be used to determine a semantic entity for the target image. The semantic entity for the target image may be used to provide search results in response to the search initiated by the target image.

Hartwig Adam

Papers

Using sensor inputs from a computing device to determine search query

Training image sampling

Learning Unified Embedding for Apparel Recognition

TubeFormer-DeepLab: Video Mask Transformer

System and method for associating images with semantic entities